Text

Mini-Batch Metropolis–Hastings With Reversible SGLD Proposal

Traditional Markov chain Monte Carlo (MCMC) algorithms are computationally intensive and do not scale well to large data. In particular, the Metropolis–Hastings (MH) algorithm requires passing over the entire dataset to evaluate the likelihood ratio in each iteration. We propose a general framework for performing MH-MCMC using mini-batches of the whole dataset and show that this gives rise to approximately a tempered stationary distribution. We prove that the algorithm preserves the modes of the original target distribution and derive an error bound on the approximation with mild assumptions on the likelihood. To further extend the utility of the algorithm to high-dimensional settings, we construct a proposal with forward and reverse moves using stochastic gradient and show that the construction leads to reasonable acceptance probabilities. We demonstrate the performance of our algorithm in both low dimensional models and high dimensional neural network applications. Particularly in the latter case, compared to popular optimization methods, our method is more robust to the choice of learning rate and improves testing accuracy. Supplementary materials for this article are available online.

Ketersediaan

Informasi Detail

Judul Seri

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION; Vol.117 No.537 March 2022

No. Panggil

-

Penerbit

: .,

Deskripsi Fisik

p. 386-394

Bahasa

English

ISBN/ISSN

-

Klasifikasi

NONE

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

NEURAL NETWORKS
TEMPERING
SCALABLE MCMC

Info Detail Spesifik

https://doi.org/10.1080/01621459.2020.1782222

Pernyataan Tanggungjawab

Tung-Yu Wu, Y. X. Rachel Wang, Wing H. Wong

Versi lain/terkait

Lampiran Berkas

Komentar